Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Use a more robust parser when parsing the outline generated by pdftohtml

Browse Source
This commit is contained in:
Kovid Goyal 2015-12-19 18:54:43 +05:30
parent 5a7b251025
commit 2326e936ff
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/calibre/ebooks/pdf/pdftohtml.py
View File

@ -125,8 +125,9 @@ def pdftohtml(output_dir, pdf_path, no_images, as_xml=False):
def parse_outline(raw, output_dir): def parse_outline(raw, output_dir):
from lxml import etree from lxml import etree
from calibre.ebooks.oeb.parse_utils import RECOVER_PARSER
raw = clean_xml_chars(xml_to_unicode(raw, strip_encoding_pats=True, assume_utf8=True)[0]) raw = clean_xml_chars(xml_to_unicode(raw, strip_encoding_pats=True, assume_utf8=True)[0])
outline = etree.fromstring(raw).xpath('(//outline)[1]') outline = etree.fromstring(raw, parser=RECOVER_PARSER).xpath('(//outline)[1]')
if outline: if outline:
from calibre.ebooks.oeb.polish.toc import TOC, create_ncx from calibre.ebooks.oeb.polish.toc import TOC, create_ncx
outline = outline[0] outline = outline[0]